The demand for multicore processors has significantly increased with the rapid advancement in technology. Effective thermal managements for multicore processors are crucial for extending their operational lifespan. This paper estimates the core temperature of multi-core processors based on the membrane potential of the spiking neural network (SNN). This research collects hardware information of multi-core processors on real machines and estimates the temperature of the processor based on spiking neural network. We use proxy gradients to implement network updates and propose an AMP method to represent temperature. Experimental results reveal that the MAPE between estimated and actual processor temperatures averages almost around 7%, demonstrating the method’s high generalizability across various continuous value regression problems. In addition, the code for collecting the dataset used in this paper will be publicly available.
No takes yet. Share an insight, caveat, or question.
Xiong et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: